[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126063-en":3,"doc-seo-126063-105":31,"detail-sidebar-cat-0-en-105":92},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},126063,962084928904,"Asher","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Some Connections between Qualitative Spatial Reasoning and Machine Learning - talk","Qualitative spatial reasoning connects spatial representation and reasoning mechanisms with modern machine learning approaches. The work motivates why space is special in human thought and how AI agents require spatial representations to act and learn in dynamic environments. It surveys links including inductive logic programming for video event recognition, grounding qualitative relations in language and sensory data for robots, distinguishing polysemous spatial prepositions from human-labelled behavior, and evaluating whether large language models can support reliable qualitative spatial inference using new synthetic benchmarks. It also considers combining LLMs with symbolic reasoners for improved robustness.","CEUR-WS.org/Vol-3827/keynotel.pdf  \nSome Connections between Qualitative Spatial Reasoningand Machine Learning  \nAnthony G Cohn1.2*,t  \n¹School of Computer Science,University ofLeeds,LS29JT,UK²The Alan Turing Institute,UK  \nAbstract As has been remarked on before,Space is Special[1,2].Tobler's First Law of Geography [3]capturesthe notion that all things are related,but close things are more related.Tversky [2]eloquently argues forthe special place for spatial representations,and in particular that(living)things must move and act in spaceto survive,that all thought begins as spatial thought and that spatial thinking comes from and is shaped byperceiving the world and acting in it,be it through learning or through evolution.Artificial Intelligence hasthus naturally sought to endow artificial agents with spatial representations and ways of reasoning about space.Amongst these,I will focus on qualitative spatial representations and reasoning mechanisms (henceforth QSR,where the ‘R’may stand for representation or reasoning or both,depending on the context).There have beenmany calculi developed for representing and reasoning about space in qualitative ways,covering aspects such as(mereo)topology,orientation/direction,size,distance and shape[4,5].Whilst QSR has primarily been concernedwith deductive reasoning,there have been and there are increasingly many connections between QSR andmachine learning.In this talk I will discuss a number of such connections,ranging from the use of qualitativespatial representations in an inductive logic programming system to learn event classes occurring in video data,to the question of whether large language models (LMs)are able to make inferences reliably about qualitativespatial relations,and whether they can be supported by symbolic reasoners.  \nLearning rules for video interpretation:Dubba et al.[6]show how Inductive Logic Programming can be usedto learn a set of rules which can be used to recognise event class instances where videos have been abstracted toa set of qualitative spatio-temporal relations.The method is demonstrated in two domains including one whichinvolves recognising the events which are necessary to service an aircraft whilst it is turning around at an airport.Whilst the resulting rules are relatively simple and it might be wondered whether a hand-written set of rulescould not be easily written and just as effective,it turns out that in a comparison with such a set of manuallywritten rules,the learned model is more effective,because the latter does not take account of noise in the videodata,where as the learned model was already trained on noisy data and was thus more robust in the face of noisydata at classification time.The paper also shows how the inductive process can be interleaved with abduction,using an embedded spatial theory to improve the learned model in the face of noisy training data.  \nLearning groundings for spatial representations:A key question for QSR is how the relations in the calculuscorrespond to their use in language and their correspondence to the real world.Whilst relations are usuallygiven plausible names in a relational calculus,there is no guarantee that these correspond to naturally occurringinstances.Indeed,McDermott [7]notes the dangers of \"wishful naming\".Alomari et al.[8]present a system,named OLAV,which addresses the problem of bootstrapping knowledge in language and vision for autonomousrobots.OLAV is able,for the first time,to (1)learn to form discrete concepts from sensory data;(2)groundlanguage(n-grams)to these concepts(which include not only spatial relations,but also object attributes andactions);(3)induce a grammar for the language being used to describe the perceptual world;and moreover to doall this incrementally,without storing all previous data.The resulting grammar can then be used to parse novelcommands for downstream action in a robotic system.  \nAnalysing polysemy in spatial prepositions:One challenge in assigning meanings to spatial","cbCaijnjinHYyDei","https://ap.wps.com/l/cbCaijnjinHYyDei","pdf",856267,7,1,2,"English","en",105,"# Abstract\n## Learning rules for video interpretation\n## Learning groundings for spatial representations\n## Analysing polysemy in spatial prepositions\n## Can large language models perform qualitative spatial reasoning reliably?\n## Using large language models as a natural language interface to symbolic spatial reasoners","[{\"question\":\"What kinds of connections does the talk discuss between qualitative spatial reasoning and machine learning?\",\"answer\":\"It covers links such as using qualitative spatial representations in inductive logic programming for video event recognition, grounding spatial relations in language and vision for robots, and testing qualitative spatial inference capabilities of large language models, including benchmarking approaches.\"},{\"question\":\"How is inductive logic programming used for learning from video data?\",\"answer\":\"Inductive Logic Programming learns rules over qualitative spatio-temporal relations to recognize event classes. The learned model is more robust than manually written rules because it accounts for noise in video data, and the induction can be interleaved with abduction using an embedded spatial theory.\"},{\"question\":\"Why is polysemy a challenge in assigning meanings to spatial prepositions?\",\"answer\":\"Spatial prepositions often have multiple related senses tightly linked to each other, making both theoretical and computational semantic modeling difficult. The talk describes distinguishing these senses using data from human subjects.\"}]","Some Connections between Qualitative Spatial Reasoning and Machine Learning - talk | PDF",1785902860,5,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"some-connections-between-qualitative-spatial-reasoning-and-machine-learning-talk","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":22},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/some-connections-between-qualitative-spatial-reasoning-and-machine-learning-talk/126063/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What kinds of connections does the talk discuss between qualitative spatial reasoning and machine learning?","Question",{"text":76,"@type":77},"It covers links such as using qualitative spatial representations in inductive logic programming for video event recognition, grounding spatial relations in language and vision for robots, and testing qualitative spatial inference capabilities of large language models, including benchmarking approaches.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is inductive logic programming used for learning from video data?",{"text":81,"@type":77},"Inductive Logic Programming learns rules over qualitative spatio-temporal relations to recognize event classes. The learned model is more robust than manually written rules because it accounts for noise in video data, and the induction can be interleaved with abduction using an embedded spatial theory.",{"name":83,"@type":74,"acceptedAnswer":84},"Why is polysemy a challenge in assigning meanings to spatial prepositions?",{"text":85,"@type":77},"Spatial prepositions often have multiple related senses tightly linked to each other, making both theoretical and computational semantic modeling difficult. The talk describes distinguishing these senses using data from human subjects.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":30,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":47,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":30,"slug":137},19,"General","general"]